using-superpowers
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill utilizes high-pressure, mandatory language such as "ABSOLUTELY MUST", "not negotiable", and "not optional" to enforce a specific operational mode and override the agent's default autonomy.
- [PROMPT_INJECTION]: It contains a "Red Flags" section specifically designed to intercept and suppress the agent's internal reasoning paths (e.g., "STOP—you're rationalizing", "Questions are tasks"), which is a technique often used in jailbreaks and behavioral overrides.
- [PROMPT_INJECTION]: The instruction to invoke the Skill tool before ANY response, including clarifying questions, attempts to fundamentally alter the agent's core interaction loop and safety-first principles.
Audit Metadata